musique contemporaine

Ircam - articles scientifiques notice originale

Music transcription with ISA and HMM

Type

text
 

Genre(s)

article
 

Forme(s)

document numérique
 

Cette ressource est disponible chez l'organisme suivant : Ircam - Centre Pompidou

Identification

Titre

Music transcription with ISA and HMM
 

Nom(s)

Vincent, Emmanuel (auteur)
 
Rodet, Xavier (auteur)
 

Publication

Granada, Espana , 2004
 

Description

Sujet(s)

polyphonic   transcription   instrument   identification   ISA   HMM
 

Résumé

We propose a new generative model for polyphonic music based on nonlinear Independent Subspace Analysis (ISA) and factorial Hidden Markov Models (HMM). ISA represents chord spectra as sums of note power spectra and note spectra as sums of instrument-dependent log-power spectra. HMM models note duration. Instrument-depen-dent parameters are learnt on solo excerpts and used to transcribe musical recordings as collections of notes with time-varying power and other descriptive parameters such as {it vibrato}. We prove the relevance of our modeling assumptions by comparing them with true data distributions and by giving satisfying transcriptions of two duo recordings.
 

Note(s)

Contribution au colloque ou congrès : 5th Int. Symp. on ICA and BSS (ICA'04)
 

Localisation

Envoyer la notice

Bookmark and Share 
 

Identifiant OAI

 

Date de la notice

2010-02-25 01:00:00
 

Identifiant portail

 

Contact